Recent developments in modeling, imaging, and monitoring of cardiovascular diseases using machine learning

Machine Learning-Based Predictive Models for Detection of Cardiovascular Diseases

Cardiovascular diseases present a significant global health challenge that emphasizes the critical need for developing accurate and more effective detection methods. Several studies have contributed valuable insights in this field, but it is still necessary to advance the predictive models and address the gaps in the existing detection approaches. For instance, some of the previous studies have not considered the challenge of imbalanced datasets, which can lead to biased predictions, especially when the datasets include minority classes. This study's primary focus is the early detection of heart diseases, particularly myocardial infarction, using machine learning techniques. It tackles the challenge of imbalanced datasets by conducting a comprehensive literature review to identify effective strategies. Seven machine learning and deep learning classifiers, including K-Nearest Neighbors, Support Vector Machine, Logistic Regression, Convolutional Neural Network, Gradient Boost, XGBoost, and Random Forest, were deployed to enhance the accuracy of heart disease predictions. The research explores different classifiers and their performance, providing valuable insights for developing robust prediction models for myocardial infarction. The study's outcomes emphasize the effectiveness of meticulously fine-tuning an XGBoost model for cardiovascular diseases. This optimization yields remarkable results: 98.50% accuracy, 99.14% precision, 98.29% recall, and a 98.71% F1 score. Such optimization significantly enhances the model's diagnostic accuracy for heart disease.

A simplified coronary model for diagnosis of ischemia-causing coronary stenosis

BACKGROUND AND OBJECTIVE

The functional assessment of the severity of coronary stenosis from coronary computed tomography angiography (CCTA)-derived fractional flow reserve (FFR) has recently attracted interest. However, existing algorithms run at high computational cost. Therefore, this study proposes a fast calculation method of FFR for the diagnosis of ischemia-causing coronary stenosis.

METHODS

We combined CCTA and machine learning to develop a simplified single-vessel coronary model for rapid calculation of FFR. First, a zero-dimensional model of single-vessel coronary was established based on CCTA, and microcirculation resistance was determined through the relationship between coronary pressure and flow. In addition, a coronary stenosis model based on machine learning was introduced to determine stenosis resistance. Computational FFR (cFFR) was then obtained by combining the zero-dimensional model and the stenosis model with inlet boundary conditions for resting (cFFRr) and hyperemic (cFFRh) aortic pressure, respectively. We retrospectively analyzed 75 patients who underwent clinically invasive FFR (iFFR), and verified the model accuracy by comparison of cFFR with iFFR.

RESULTS

The average computing time of cFFR was less than 2 s. The correlations between cFFRr and cFFRh with iFFR were r = 0.89 (p < 0.001) and r = 0.90 (p < 0.001), respectively. Diagnostic accuracy, sensitivity, specificity, positive predictive value, negative predictive value, positive likelihood ratio, negative likelihood ratio for cFFRr and cFFRh were 90.7%, 95.0%, 89.1%, 76.0%, 98.0%, 8.7, 0.1 and 92.0%, 95.0%, 90.9%, 79.2%, 98.0%, 10.5, 0.1, respectively.

CONCLUSIONS

The proposed model enables rapid prediction of cFFR and exhibits high diagnostic performance in selected patient cohorts. The model thus provides an accurate and time-efficient computational tool to detect ischemia-causing stenosis and assist with clinical decision-making.

Physics-informed neural networks (PINNs) for 4D hemodynamics prediction: An investigation of optimal framework based on vascular morphology

Hemodynamic parameters are of great significance in the clinical diagnosis and treatment of cardiovascular diseases. However, noninvasive, real-time and accurate acquisition of hemodynamics remains a challenge for current invasive detection and simulation algorithms. Here, we integrate computational fluid dynamics with our customized analysis framework based on a multi-attribute point cloud dataset and physics-informed neural networks (PINNs)-aided deep learning modules. This combination is implemented by our workflow that generates flow field datasets within two types of patient personalized models - aorta with fine coronary branches and abdominal aorta. Deep learning modules with or without an antecedent hierarchical structure model the flow field development and complete the mapping from spatial and temporal dimensions to 4D hemodynamics. 88,000 cases on 4 randomized partitions in 16 controlled trials reveal the hemodynamic landscape of spatio-temporal anisotropy within two types of personalized models, which demonstrates the effectiveness of PINN in predicting the space-time behavior of flow fields and gives the optimal deep learning framework for different blood vessels in terms of balancing the training cost and accuracy dimensions. The proposed framework shows intentional performance in computational cost, accuracy and visualization compared to currently prevalent methods, and has the potential for generalization to model flow fields and corresponding clinical metrics within vessels at different locations. We expect our framework to push the 4D hemodynamic predictions to the real-time level, and in statistically significant fashion, applicable to morphologically variable vessels.

Biophysical Reviews: Turning the page from 2022 to 2023

This Editorial (vol. 15 issue 1-Regular Issue featuring an Issue Focus on the "100th Anniversary of Har Gobind Khorana") first describes the issue contents before providing both, a look back at some journal highlights from 2022, and a look forward to what we can expect from 2023. The Editorial closes with a roundup of new journal access features and an acknowledgement of those supporting the journal.